arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.05321cs.CVcs.AI
收藏

一种用于基于事件的目标检测的循环 YOLOv8 框架

A Recurrent YOLOv8-based framework for Event-Based Object Detection

Cairo University(开罗大学);Compumacy for Artificial Intelligence solutions(Compumacy人工智能解决方案公司)

Diego A. Silva, Kamilya Smagulova, Ahmed Elsheikh, Mohammed E. Fouda, Ahmed M. Eltawil

AI总结:

提出 ReYOLOv8 循环事件目标检测框架,结合高效事件编码与专用数据增强,在 GEN1 和 PEDRo 上实现更高 mAP、更小模型与实时推理。

摘要:

目标检测在自动驾驶车辆和先进机器人系统等各种前沿应用中至关重要,其主要依赖来自传统基于帧的 RGB 传感器的数据。然而,这些传感器往往难以应对运动模糊以及在挑战性光照条件下性能不佳等问题。为应对这些挑战,基于事件的相机已成为一种创新范式。这些相机模拟人眼,在快速运动和极端光照条件的环境中表现出优越性能,同时功耗更低。本研究提出 ReYOLOv8,这是一种先进的目标检测框架,通过时空建模能力增强领先的基于帧的检测系统。我们实现了一种低延迟、内存高效的事件数据编码方法,以提升系统性能。我们还开发了一种新颖的数据增强技术,专门用于利用事件数据的独特属性,从而提高检测精度。我们的模型在聚焦汽车应用的 GEN1 数据集上优于所有可比方法,在 nano、small 和 medium 规模上分别实现了 5%、2.8% 和 2.5% 的平均精度均值(mAP)提升。在实现这些增强的同时,可训练参数数量平均减少 4.43%,并保持 9.2ms 至 15.5ms 的实时处理速度。在面向机器人应用的 PEDRo 数据集上,我们的模型显示出 9% 至 18% 的 mAP 提升,模型体积分别缩小 14.5 倍和 3.8 倍,平均速度提升 1.67 倍。

英文摘要:

Object detection is crucial in various cutting-edge applications, such as autonomous vehicles and advanced robotics systems, primarily relying on data from conventional frame-based RGB sensors. However, these sensors often struggle with issues like motion blur and poor performance in challenging lighting conditions. In response to these challenges, event-based cameras have emerged as an innovative paradigm. These cameras, mimicking the human eye, demonstrate superior performance in environments with fast motion and extreme lighting conditions while consuming less power. This study introduces ReYOLOv8, an advanced object detection framework that enhances a leading frame-based detection system with spatiotemporal modeling capabilities. We implemented a low-latency, memory-efficient method for encoding event data to boost the system's performance. We also developed a novel data augmentation technique tailored to leverage the unique attributes of event data, thus improving detection accuracy. Our models outperformed all comparable approaches in the GEN1 dataset, focusing on automotive applications, achieving mean Average Precision (mAP) improvements of 5%, 2.8%, and 2.5% across nano, small, and medium scales, respectively.These enhancements were achieved while reducing the number of trainable parameters by an average of 4.43% and maintaining real-time processing speeds between 9.2ms and 15.5ms. On the PEDRo dataset, which targets robotics applications, our models showed mAP improvements ranging from 9% to 18%, with 14.5x and 3.8x smaller models and an average speed enhancement of 1.67x.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑